Viewing 1-10 of 307 papers
  • Abductive Commonsense Reasoning

    Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Scott Wen-tau Yih, Yejin ChoiICLR2020Abductive reasoning is inference to the most plausible explanation. For example, if Jenny finds her house in a mess when she returns from work, and remembers that she left a window open, she can hypothesize that a thief broke into her house and caused the mess, as the most plausible explanation… more
  • Differentiable Scene Graphs

    Moshiko Raboh, Roei Herzig, Gal Chechik, Jonathan Berant, Amir Globerson WACV2020Understanding the semantics of complex visual scenes involves perception of entities and reasoning about their relations. Scene graphs provide a natural representation for these tasks, by assigning labels to both entities (nodes) and relations (edges). However, scene graphs are not commonly used as… more
  • Adversarial Filters of Dataset Biases

    Ronan Le Bras, Swabha Swayamdipta, Chandra Bhagavatula, Rowan Zellers, Matthew E. Peters, Ashish Sabharwal, Yejin Choi arXiv2020Large neural models have demonstrated humanlevel performance on language and vision benchmarks such as ImageNet and Stanford Natural Language Inference (SNLI). Yet, their performance degrades considerably when tested on adversarial or out-of-distribution samples. This raises the question of whether… more
  • Transformers as Soft Reasoners over Language

    Peter Clark, Oyvind Tafjord, Kyle RichardsonarXiv2020AI has long pursued the goal of having systems reason over explicitly provided knowledge, but building suitable representations has proved challenging. Here we explore whether transformers can similarly learn to reason (or emulate reasoning), but using rules expressed in language, thus bypassing a… more
  • WinoGrande: An Adversarial Winograd Schema Challenge at Scale

    Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, Yejin ChoiAAAI2020The Winograd Schema Challenge (WSC), proposed by Levesque et al. (2011) as an alternative to the Turing Test, was originally designed as a pronoun resolution problem that cannot be solved based on statistical patterns in large text corpora. However, recent studies suggest that current WSC datasets… more
  • QASC: A Dataset for Question Answering via Sentence Composition

    Tushar Khot, Peter Clark, Michal Guerquin, Paul Edward Jansen, Ashish Sabharwal AAAI2020Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus and composing them to answer a multiple-choice… more
  • Probing Natural Language Inference Models through Semantic Fragments

    Kyle Richardson, Hai Na Hu, Lawrence S. Moss, Ashish SabharwalAAAI2020Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word substitutions in sentential contexts)? While such phenomena are… more
  • MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity

    Hai Hu, Qi Chen, Kyle Richardson, Atreyee Mukherjee, Lawrence S. Moss, Sandra Kübler SCIL2020We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using… more
  • oLMpics - On what Language Model Pre-training Captures

    Alon Talmor, Yanai Elazar, Yoav Goldberg, Jonathan BerantarXiv2019Recent success of pre-trained language models (LMs) has spurred widespread interest in the language capabilities that they possess. However, efforts to understand whether LM representations are useful for symbolic reasoning tasks have been limited and scattered. In this work, we propose eight… more
  • What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge

    Kyle Richardson, Ashish SabharwalarXiv2019Open-domain question answering (QA) is known to involve several underlying knowledge and reasoning challenges, but are models actually learning such knowledge when trained on benchmark tasks? To investigate this, we introduce several new challenge tasks that probe whether state-of-theart QA models… more